© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64699
    Prev
    Next
    INDEX
    Explanations

    Red Cross Society

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on mentions of the “Red Cross” (and related Red Cross society acronyms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     excise
    -0.74
    konom
    -0.74
    Wage
    -0.71
     đặc
    -0.71
    ᅢ
    -0.70
    ensen
    -0.68
    istan
    -0.68
    thanes
    -0.68
    Gabe
    -0.67
    🅻
    -0.66
    POSITIVE LOGITS
     Red
    2.88
    Red
    2.48
     red
    1.73
    紅
    1.73
    红
    1.63
    RED
    1.54
     红
    1.50
     RED
    1.46
     humanitarian
    1.46
     レッド
    1.38
    Activations Density 0.016%

    No Known Activations